MMD

Australian team wins 2017 Amazon robotics challenge

Contestants at this year's Amazon Robotics Challenge were awarded $270,000 in prizes to support continued innovation within the robotics and automation community


August 2, 2017
by

Day one of the third annual Amazon Robotics Challenge, held in conjunction with RoboCup, in Nagoya, Japan. (JORDAN STEAD / Amazon)

SEATTLE, Washington — The Australian Centre for Robotic Vision has won the 2017 Amazon Robotics Challenge. The team succeeded in the Grand Championship Combined Task to win the overall Challenge, with Nanyang Technological University of Singapore winning the Pick Task and MIT Princeton of the US, winning the Stow Task.

This year’s finalists demonstrated sophisticated solutions combining object recognition, pose recognition, grasp planning, compliant manipulation, motion planning, task planning, task execution, and error detection and recovery to successfully pick and stow unique items.

Teams were judged based on how many items were successfully picked and stowed by their robots in a fixed amount of time. A total of $270,000 in prizes were awarded to contestants throughout the four-day competition.

The Amazon Robotics Challenge aims to strengthen the ties between the industrial and academic robotic communities and promote shared and open solutions to the technical challenges faced in unstructured automation.

This year’s Amazon Robotics Challenge was held during RoboCup, the leading and most diverse competition for intelligent robots and one of the world’s most important technology events in research and training. RoboCup and the Amazon Robotics Challenge were held in Japan at the Nagoya International Exhibition Hall (Portmesse Nagoya).

“This year, we made some changes to the Challenge to make it even more difficult and to encourage broader participation from multiple robotics fields – and the response was exciting,” said Joey Durham, contest chairperson and manager of research and advanced development for Amazon Robotics.

“The versatility of recognition capabilities in an unstructured environment and the dexterity of grasping mechanisms was truly impressive. What we’re most proud of with the Amazon Robotics Challenge is its celebration of robotic community and the venue it’s created to share and promote research in a fun and rewarding way. Congratulations to our winners and all of our contestants!”

The Australian Centre for Robotic Vision team consisted of researchers, early PhD candidates and undergraduate students who combined computer vision, machine learning and a variety of robotic hardware to successfully complete both pick and stow tasks the fastest.

Below is additional information on all winners.

Grand Championship in Combined Task

Winning team

University/organization

Country

Award

1st ACRV Australian Center for Robotic Vision Australia $80,000
2nd NimbRo University of Bonn Germany $40,000
3rd Nanyang Nanyang Technological University Singapore $20,000

Pick Task

Winning team

University/organization

Country

Award

1st Nanyang Nanyang Technological University Singapore $20,000
2nd NimbRo Picking University of Bonn Germany $10,000
3rd IITK TCS Indian Institute of Technology Kanpur, Tata Consultancy Services India $5,000

Stow Task

Winning team

University/organization

Country

Award

1st MIT-Princeton MIT-Princeton USA $20,000
2nd Nanyang Nanyang Technological University, Singapore $10,000
3rd MC^2 Mitsubishi Electric, Chubu University, Chukyo University Japan $5,000

Amazon is committed to supporting innovation in robotics and automation. The company utilizes a wide range of innovative technology within its fulfillment centres, including more than 100,000 Amazon Robotics drive units in over 25 fulfillment centres worldwide. Amazon Robotics drive units deliver items directly to employees at ergonomic work stations and help make associates’ roles more efficient.

For additional information about the Amazon Robotics Challenge including contest details, participating teams, rules, FAQs and detailed results, visit www.amazonrobotics.com/#/roboticschallenge. For more information about RoboCup, visit www.robocup2017.org. A video from the event can be viewed here.